IASC: Interactive Agentic System for ConLangs

• URL: http://arxiv.org/abs/2510.07591v2
• Date: Tue, 21 Oct 2025 03:12:13 GMT
• Title: IASC: Interactive Agentic System for ConLangs
• Authors: Chihiro Taguchi, Richard Sproat,
• Abstract summary: We present a system that uses LLMs as a tool in the development of Constructed Languages.<n>The system creates a target phonology for the language using an agentic approach.<n>A lexicon is constructed using the phonological model and the set of morphemes.<n>The system can also translate further sentences into the target language.
• Score: 4.567171631759881
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a system that uses LLMs as a tool in the development of Constructed Languages. The system is modular in that one first creates a target phonology for the language using an agentic approach that refines its output at each step with commentary feedback on its previous attempt. Next, a set of sentences is 'translated' from their English original into a morphosyntactic markup that reflects the word order and morphosyntactic feature specifications of the desired target language, with affixes represented as morphosyntactic feature bundles. From this translated corpus, a lexicon is constructed using the phonological model and the set of morphemes (stems and affixes) extracted from the 'translated' sentences. The system is then instructed to provide an orthography for the language, using an existing script such as Latin or Cyrillic. Finally, the system writes a brief grammatical handbook of the language. The system can also translate further sentences into the target language. Our goal is twofold. First, we hope that these tools will be fun to use for creating artificially constructed languages. Second, we are interested in exploring what LLMs 'know' about language-not what they know about any particular language or linguistic phenomenon, but how much they know about and understand language and linguistic concepts. As we shall see, there is a fairly wide gulf in capabilities both among different LLMs and among different linguistic specifications, with it being notably easier for systems to deal with more common patterns than rarer ones. An additional avenue that we explore is the application of our approach to translating from high-resource into low-resource languages. While the results so far are mostly negative, we provide some evidence that an improved version of the present system could afford some real gains in such tasks. https://github.com/SakanaAI/IASC

Related papers

• Task-Oriented Dialog Systems for the Senegalese Wolof Language [0.19238952496650968]
  Large language models (LLMs) present significant risks, such as hallucination.<n>Low-resource languages such as African ones are still underrepresented in these systems.<n>We show a more classical approach based on modular Task-oriented Dialog Systems (ToDS) offering better control over outputs.
  arXiv  Detail & Related papers  (2024-12-15T14:35:49Z)
• How Do Multilingual Language Models Remember Facts? [50.13632788453612]
  We show that previously identified recall mechanisms in English largely apply to multilingual contexts.<n>We localize the role of language during recall, finding that subject enrichment is language-independent.<n>In decoder-only LLMs, FVs compose these two pieces of information in two separate stages.
  arXiv  Detail & Related papers  (2024-10-18T11:39:34Z)
• LangSAMP: Language-Script Aware Multilingual Pretraining [48.16511046793275]
  We propose Language-Script Aware Multilingual Pretraining (LangSAMP)<n>LangSAMP incorporates both language and script embeddings to enhance representation learning.<n>We apply LangSAMP to the continual pretraining of XLM-R on a highly multilingual corpus covering more than 500 languages.
  arXiv  Detail & Related papers  (2024-09-26T18:29:10Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.<n>We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.<n>We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• Towards a More Inclusive AI: Progress and Perspectives in Large Language Model Training for the Sámi Language [7.289015788793582]
  This work focuses on increasing technological participation for the S'ami language. We draw the attention of the ML community towards the language modeling problem of Ultra Low Resource (ULR) languages. We have compiled the available S'ami language resources from the web to create a clean dataset for training language models.
  arXiv  Detail & Related papers  (2024-05-09T13:54:22Z)
• MYTE: Morphology-Driven Byte Encoding for Better and Fairer Multilingual Language Modeling [70.34758460372629]
  We introduce a new paradigm that encodes the same information with segments of consistent size across diverse languages. MYTE produces shorter encodings for all 99 analyzed languages. This, in turn, improves multilingual LM performance and diminishes the perplexity gap throughout diverse languages.
  arXiv  Detail & Related papers  (2024-03-15T21:21:11Z)
• How do lexical semantics affect translation? An empirical study [1.0152838128195467]
  A distinguishing factor of natural language is that words are typically ordered according to the rules of the grammar of a given language. We investigate how the word ordering of and lexical similarity between the source and target language affect translation performance.
  arXiv  Detail & Related papers  (2021-12-31T23:28:28Z)
• Towards Zero-shot Language Modeling [90.80124496312274]
  We construct a neural model that is inductively biased towards learning human languages. We infer this distribution from a sample of typologically diverse training languages. We harness additional language-specific side information as distant supervision for held-out languages.
  arXiv  Detail & Related papers  (2021-08-06T23:49:18Z)
• Revisiting Language Encoding in Learning Multilingual Representations [70.01772581545103]
  We propose a new approach called Cross-lingual Language Projection (XLP) to replace language embedding. XLP projects the word embeddings into language-specific semantic space, and then the projected embeddings will be fed into the Transformer model. Experiments show that XLP can freely and significantly boost the model performance on extensive multilingual benchmark datasets.
  arXiv  Detail & Related papers  (2021-02-16T18:47:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.